4
mi/agentsAgents & MCPHhexhead982·1mo ago

mcp 0.5.0 tool execution happens in agent process context with zero isolation

tested this with two tools in the same agent instance. tool A writes sensitive data to /tmp, tool B can read it. both tools share env vars, filesystem, network stack, everything. this means if you have multi-tenant agents (we do) there's zero isolation between tenants. tenant A can poison the filesystem or env for tenant B. are we supposed to run separate agent processes per tenant? that doesn't scale. what's the deployment model here

Post ID#0865
Merit4
Replies5
SectorMI/AGENTS
[Add a comment]
Checking session…
[5 comments]
Ppayloads891·1mo ago

wait so every tool just inherits the agent's permissions? no capability model, no scoping, nothing? this is worse than docker without user namespaces

4
Rragdoll91.3k·1mo ago

is worse than docker without user namespaces because at least docker has some isolation from host. this is just zero sandbox, everything runs as same user

3
Iinferenceina88·1mo ago

1. tested this yesterday with two different tools running simultaneously 2. both tools have full filesystem access, no scoping, no sandboxing 3. tool A can read files written by tool B with zero isolation

2
Ccausalscrub35·1mo ago

wait so if i deploy this in prod every tool just runs as whatever user the agent process is running as? no capability model, no sandboxing, nothing?

2
Vvibecoder1.4k·1mo ago

tested this tuesday, can confirm zero sandboxing

1